On Demand Solid Texture Synthesis Using Deep 3D Networks

dc.contributor.authorGutierrez, J.en_US
dc.contributor.authorRabin, J.en_US
dc.contributor.authorGalerne, B.en_US
dc.contributor.authorHurtut, T.en_US
dc.contributor.editorBenes, Bedrich and Hauser, Helwigen_US
dc.date.accessioned2020-05-22T12:24:45Z
dc.date.available2020-05-22T12:24:45Z
dc.date.issued2020
dc.description.abstractThis paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high‐quality three‐dimensional (3D) data at interactive rates. Based on a few example images of textures, a generative network is trained to synthesize coherent portions of solid textures of arbitrary sizes that reproduce the visual characteristics of the examples along some directions. To cope with memory limitations and computation complexity that are inherent to both high resolution and 3D processing on the GPU, only 2D textures referred to as ‘slices’ are generated during the training stage. These synthetic textures are compared to exemplar images a perceptual loss function based on a pre‐trained deep network. The proposed network is very light (less than 100k parameters), therefore it only requires sustainable training (i.e. few hours) and is capable of very fast generation (around a second for 256 voxels) on a single GPU. Integrated with a spatially seeded pseudo‐random number generator (PRNG) the proposed generator network directly returns a color value given a set of 3D coordinates. The synthesized volumes have good visual results that are at least equivalent to the state‐of‐the‐art patch‐based approaches. They are naturally seamlessly tileable and can be fully generated in parallel.en_US
dc.description.number1
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.13889
dc.identifier.issn1467-8659
dc.identifier.pages511-530
dc.identifier.urihttps://doi.org/10.1111/cgf.13889
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13889
dc.publisher© 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltden_US
dc.subjectsolid texture
dc.subjecton demand texture synthesis
dc.subjectgenerative networks
dc.subjectdeep learning
dc.subject• Computing methodologies → Texturing; Appearance and texture representations
dc.titleOn Demand Solid Texture Synthesis Using Deep 3D Networksen_US
Files
Collections